Enhance synchscope representation

  OpenCL 2.0 introduces the notion of memory scopes in atomic operations to
  global and local memory. These scopes restrict how synchronization is
  achieved, which can result in improved performance.

  This change extends existing notion of synchronization scopes in LLVM to
  support arbitrary scopes expressed as target-specific strings, in addition to
  the already defined scopes (single thread, system).

  The LLVM IR and MIR syntax for expressing synchronization scopes has changed
  to use *syncscope("<scope>")*, where <scope> can be "singlethread" (this
  replaces *singlethread* keyword), or a target-specific name. As before, if
  the scope is not specified, it defaults to CrossThread/System scope.

  Implementation details:
    - Mapping from synchronization scope name/string to synchronization scope id
      is stored in LLVM context;
    - CrossThread/System and SingleThread scopes are pre-defined to efficiently
      check for known scopes without comparing strings;
    - Synchronization scope names are stored in SYNC_SCOPE_NAMES_BLOCK in
      the bitcode.

Differential Revision: https://reviews.llvm.org/D21723

llvm-svn: 307722

3 files changed, 10 insertions, 10 deletions

diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 4ff9f79898f..6ba7593543a 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -3398,9 +3398,9 @@ ARMTargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG,
 static SDValue LowerATOMIC_FENCE(SDValue Op, SelectionDAG &DAG,
                                  const ARMSubtarget *Subtarget) {
   SDLoc dl(Op);
-  ConstantSDNode *ScopeN = cast<ConstantSDNode>(Op.getOperand(2));
-  auto Scope = static_cast<SynchronizationScope>(ScopeN->getZExtValue());
-  if (Scope == SynchronizationScope::SingleThread)
+  ConstantSDNode *SSIDNode = cast<ConstantSDNode>(Op.getOperand(2));
+  auto SSID = static_cast<SyncScope::ID>(SSIDNode->getZExtValue());
+  if (SSID == SyncScope::SingleThread)
     return Op;
 
   if (!Subtarget->hasDataBarrier()) {
diff --git a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
index 937bb6d229d..2801141cd95 100644
--- a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
@@ -3182,13 +3182,13 @@ SDValue SystemZTargetLowering::lowerATOMIC_FENCE(SDValue Op,
   SDLoc DL(Op);
   AtomicOrdering FenceOrdering = static_cast<AtomicOrdering>(
     cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue());
-  SynchronizationScope FenceScope = static_cast<SynchronizationScope>(
+  SyncScope::ID FenceSSID = static_cast<SyncScope::ID>(
     cast<ConstantSDNode>(Op.getOperand(2))->getZExtValue());
 
   // The only fence that needs an instruction is a sequentially-consistent
   // cross-thread fence.
   if (FenceOrdering == AtomicOrdering::SequentiallyConsistent &&
-      FenceScope == CrossThread) {
+      FenceSSID == SyncScope::System) {
     return SDValue(DAG.getMachineNode(SystemZ::Serialize, DL, MVT::Other,
                                       Op.getOperand(0)),
                    0);
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 4e160eccb3a..3d08037e728 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -22850,7 +22850,7 @@ X86TargetLowering::lowerIdempotentRMWIntoFencedLoad(AtomicRMWInst *AI) const {
 
   auto Builder = IRBuilder<>(AI);
   Module *M = Builder.GetInsertBlock()->getParent()->getParent();
-  auto SynchScope = AI->getSynchScope();
+  auto SSID = AI->getSyncScopeID();
   // We must restrict the ordering to avoid generating loads with Release or
   // ReleaseAcquire orderings.
   auto Order = AtomicCmpXchgInst::getStrongestFailureOrdering(AI->getOrdering());
@@ -22872,7 +22872,7 @@ X86TargetLowering::lowerIdempotentRMWIntoFencedLoad(AtomicRMWInst *AI) const {
   // otherwise, we might be able to be more aggressive on relaxed idempotent
   // rmw. In practice, they do not look useful, so we don't try to be
   // especially clever.
-  if (SynchScope == SingleThread)
+  if (SSID == SyncScope::SingleThread)
     // FIXME: we could just insert an X86ISD::MEMBARRIER here, except we are at
     // the IR level, so we must wrap it in an intrinsic.
     return nullptr;
@@ -22891,7 +22891,7 @@ X86TargetLowering::lowerIdempotentRMWIntoFencedLoad(AtomicRMWInst *AI) const {
   // Finally we can emit the atomic load.
   LoadInst *Loaded = Builder.CreateAlignedLoad(Ptr,
           AI->getType()->getPrimitiveSizeInBits());
-  Loaded->setAtomic(Order, SynchScope);
+  Loaded->setAtomic(Order, SSID);
   AI->replaceAllUsesWith(Loaded);
   AI->eraseFromParent();
   return Loaded;
@@ -22902,13 +22902,13 @@ static SDValue LowerATOMIC_FENCE(SDValue Op, const X86Subtarget &Subtarget,
   SDLoc dl(Op);
   AtomicOrdering FenceOrdering = static_cast<AtomicOrdering>(
     cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue());
-  SynchronizationScope FenceScope = static_cast<SynchronizationScope>(
+  SyncScope::ID FenceSSID = static_cast<SyncScope::ID>(
     cast<ConstantSDNode>(Op.getOperand(2))->getZExtValue());
 
   // The only fence that needs an instruction is a sequentially-consistent
   // cross-thread fence.
   if (FenceOrdering == AtomicOrdering::SequentiallyConsistent &&
-      FenceScope == CrossThread) {
+      FenceSSID == SyncScope::System) {
     if (Subtarget.hasMFence())
       return DAG.getNode(X86ISD::MFENCE, dl, MVT::Other, Op.getOperand(0));